arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

National University of Singapore(新加坡国立大学)

2026-08-18 至 2026-08-18 共收录 10
2608.13416 2026-08-18 cs.CV 版本更新

StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs

StreamTTT:在流式视觉语言模型中协调实时感知与长期记忆

Joya Chen, Zeyun Zhong, Mike Zheng Shou

机构 * National University of Singapore(新加坡国立大学) Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

AI总结 StreamTTT通过将长程历史写入注意力外的快速权重、保留短滑动键值缓存,在OVO-Bench和StreamingBench上提升了流式VLMs的实时感知与长程记忆能力,且代码将公开。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.04484 2026-08-18 cs.CV 版本更新

TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction

TrustCLIP:通过对抗性重建学习隐私视觉特征

Nikos Athanasiou, Ilya A. Petrov, Angela Yao, Shugao Ma, Eric Sauser, Edoardo Remelli, Shreyas Hampali, Johannes Schönberger, Fadime Sener, Bugra Tekin

机构 * Meta Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) University of Tübingen(图宾根大学) National University of Singapore(新加坡国立大学)

AI总结 研究视觉和视觉语言模型中视觉特征隐私问题,提出TrustCLIP框架,以特征条件生成器为隐私对手,优化编码器特征与下游模块投影,降低生成式反演保真度并保持下游任务性能。

Comments this https URL (https://atnikos.github.io/trustclip/) Update affiliations

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.27377 2026-08-18 cs.CV cs.CL cs.LG 版本更新

DanceOPD: On-Policy Generative Field Distillation

DanceOPD:在策略生成场蒸馏

Wei Zhou, Xiongwei Zhu, Zelin Xu, Bo Dong, Lixue Gong, Yongyuan Liang, Meng Chu, Leigang Qu, Lingdong Kong, Wei Liu, Tat-Seng Chua

机构 * ByteDance Seed(字节跳动Seed) NUS(新加坡国立大学) UMD(马里兰大学) HKUST(香港科技大学)

AI总结 提出DanceOPD框架,通过将每个样本路由到能力场并查询低噪声学生诱导状态,用速度MSE损失训练流匹配模型,实现文本到图像、局部编辑和全局编辑的多能力组合,提升目标能力同时保持生成质量。

Comments Technical Report; 42 pages, 14 figures, 9 tables; Project Page at this https URL (https://danceopd.github.io/) GitHub Repo at this https URL (https://github.com/worldbench/DanceOPD)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20753 2026-08-18 physics.chem-ph cs.AI 版本更新

Empowering Polymeric Materials Discovery by Artificial Intelligence

人工智能赋能高分子材料发现

Chenyao Ma, Linda Zhang, Yuheng Chen, Wei Du, Shangwen Fang, Zihao Jiang, Chuanyu Liu, Xinyu Ma, Rui Su, Gang Wang, Muyao Yu, Dong Zhong, Jie Zhu, Weibo Gong, Huan Gu, Limin Li, Chen Shen, Rui Wu, Zhenghao Wu, Kan Xu, Min Zhou, Donglin He, Xiayun Huang, Shan Jiang, Pengfei Ou, Jiayu Peng, Yuwei Zhang, Jie Zhao, Di Zhang, Piao Ma, Zhenghao Li, Hao Li

机构 * Suzhou MatSource Technology Co., Ltd.(苏州MatSource科技有限公司) Gusu Laboratory of Materials(材料Gusu实验室) Advanced Institute for Materials Research (WPI-AIMR)(先进材料研究所(WPI-AIMR)) Frontier Research Institute for Interdisciplinary Sciences (FRIS)(交叉学科前沿研究所(FRIS)) State Key Laboratory of Advanced Environmental Technology, Department of Environmental Science and Engineering, University of Science and Technology of China(先进技术国家实验室,环境科学与工程系,中国科学技术大学) Jiangsu Key Laboratory of New Power Batteries, Jiangsu Collaborative Innovation Centre of Biomedical Functional Materials, School of Chemistry and Materials Science, Nanjing Normal University(新型动力电池江苏省重点实验室,生物医学功能材料协同创新中心,化学与材料科学学院,南京师范大学) Department of Chemistry, National University of Singapore(新加坡国立大学化学系) Thrust of Sustainable Energy and Environment, The Hong Kong University of Science and Technology (Guangzhou)(可持续能源与环境方向,香港科技大学(广州)) Department of Materials Design and Innovation, University at Buffalo(材料设计与创新系,布法罗大学) College of Smart Materials and Future Energy, State Key Laboratory of Molecular Engineering of Polymers, Fudan University(智能材料与未来能源学院,聚合物分子工程国家重点实验室,复旦大学) School of Physical Science and Technology, Shanghai tech University(物理科学与技术学院,上海科技大学) The State Key Laboratory of Molecular Engineering of Polymers and Department of Macromolecular Science, Fudan University(聚合物分子工程国家重点实验室和大分子科学系,复旦大学) Department of Chemistry and Materials Science, Xi'an J Liverpool University(化学与材料科学系,西安J Liverpool大学)

AI总结 本文综述了数据基础设施、机器学习、大模型和实验室自动化如何融合成自主发现生态系统,通过自改进反馈循环实现高分子材料的预测性、可重复和可扩展创新。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04623 2026-08-18 cs.LG 版本更新

Learning symplectic model reduction based on an approximation theorem of symplectic embeddings

基于辛嵌入逼近定理的辛模型降阶学习

Liyi Feng, Yifa Tang, Yulin Xie, Ruili Zhang, Aiqing Zhu

机构 * School of Mathematics and Statistics, Beijing Jiaotong University(北京交通大学数学与统计学学院) State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院数学科学国家重点实验室) Department of Mathematics, National University of Singapore(新加坡国立大学数学系)

AI总结 针对高维哈密顿系统降阶中辛结构易破坏的问题,提出辛保持自编码器(SpAE),通过参数化解码器为辛嵌入、编码器为辛投影,在保证辛结构的同时提升重构与预测精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.09018 2026-08-18 cs.NE cs.AI cs.LG 版本更新

Evolving Ensemble of Agents

进化代理群体

Zongmin Yu, Liu Yang

机构 * National University of Singapore(新加坡国立大学)

AI总结 本文提出EvE框架,通过进化编码代理群体实现算法发现,解决了传统方法的局限,展示了自修正群体在复杂代码库中的优势。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.08974 2026-08-18 cs.CV cs.AI 版本更新

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

追踪真相:面向视频大语言模型的物体感知时空监控

Tri Cao, Khoi Le, Thong Nguyen, Cong-Duy Nguyen, Quynh Vo, Anh Tuan Luu, Chunyan Miao, See-Kiong Ng, Shuicheng Yan, Bryan Hooi

机构 * National University of Singapore(新加坡国立大学) VinUniversity(文大学) Nanyang Technological University(南洋理工大学)

AI总结 本文提出STEMO-Bench基准测试,通过分解查询验证时空监控能力,改进视频大语言模型的时空推理一致性。

Comments The authors are withdrawing this manuscript due to errors identified in the experimental evaluation and result aggregation, which affect several reported quantitative results and some conclusions. These issues require substantial re-evaluation of the experiments and analysis

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.15983 2026-08-18 cs.SE cs.AI cs.LG math.OC 版本更新

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization

ReLoop:结构建模与行为验证用于可靠的基于LLM的优化

Junbo Jacob Lian, Yujun Sun, Huiling Chen, Chaoyu Zhang, Hanzhang Qin, Chung-Piaw Teo

机构 * McCormick School of Engineering, Northwestern University(西北大学工程学院) Wenzhou Buyi Pharmacy Chain Co., Ltd.(温州-buyi药链有限公司) College of Computer Science and Artificial Intelligence, Wenzhou University(温州大学计算机科学与人工智能学院) Department of Decision Analytics and Operations, City University of Hong Kong(香港城市大学决策分析与运营部门) Institute of Operations Research and Analytics, National University of Singapore(新加坡国立大学运筹学与分析研究所)

AI总结 ReLoop通过结构生成和行为验证机制,解决LLM生成优化代码的可行性与正确性差距问题,提升代码执行准确性和鲁棒性。

Comments Code and benchmark: this https URL (https://github.com/junbolian/ReLoop)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11399 2026-08-18 cs.CV cs.CL 版本更新

Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models

层次间推理:通过层选择性融合恢复视频-语言模型中的时间推理

Zihang Fu, Haonan Wang, Jian Kang, Kenji Kawaguchi, Jiaying Wu

机构 * National University of Singapore(新加坡国立大学) MBZUAI(穆罕默德·本·扎耶德人工智能大学)

AI总结 本文提出MERIT框架,通过层选择性融合提升视频-语言模型的时间推理能力,同时保持时间感知能力,优于全模型融合和随机层选择。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12478 2026-08-18 cs.CV cs.LG 版本更新

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

数据更少,收敛更快:面向多模态指令微调的目标驱动数据优化

Rujie Wu, Haozhe Zhao, Hai Ci, Yizhou Wang

机构 * Peking University(北京大学) University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) National University of Singapore(新加坡国立大学)

AI总结 本文提出目标驱动数据优化框架GDO,通过优化训练样本实现更快收敛和更高精度,适用于多模态指令微调任务。

Comments Accepted to ECCV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏